Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: May 28, 2026

A Data-Driven Approach to Quantifying Immune States in Sepsis

A Data-Driven Approach to Quantifying Immune States in Sepsis

Published on: February 7, 2025

Privacy-Aware Synthetic Tabular Data Generation for Healthcare: Application to Sepsis Detection.

Eric Macias-Fassio^1,2, Aythami Morales^2,3, Cristina Pruenza¹

¹Instituto de Ingeniería del Conocimiento, 28049 Madrid, Spain.

Bioengineering (Basel, Switzerland)

|May 27, 2026

Summary

This summary is machine-generated.

Related Concept Videos

Issues And Trends In Healthcare Delivery System

Issues And Trends In Healthcare Delivery System

The issues and trends in healthcare delivery are constantly changing. The COVID-19 pandemic is one recent issue that wreaked havoc on healthcare systems, causing a shortage of healthcare workers, high demand for medicines and supplies, and increased medical expenditure due to a lack of insurance. Other issues include rising healthcare costs and care fragmentation.
Cost Containment
Payment for healthcare services has historically promoted adoption of costly and often unnecessary or inefficient...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Network topology of the gut microbiome associates with metabolic health in obesity.

Nature communications·2026

Same author

Personalized weight loss management through wearable devices and artificial intelligence.

Computers in biology and medicine·2026

Same author

Hospital-Wide Sepsis Detection: A Machine Learning Model Based on Prospectively Expert-Validated Cohort.

Journal of clinical medicine·2026

Same author

A multimodal dataset for understanding the impact of mobile phones on remote online virtual education.

Scientific data·2025

Same author

Oxidative Stress and Inflammation in Hypoxemic Respiratory Diseases and Their Comorbidities: Molecular Insights and Diagnostic Advances in Chronic Obstructive Pulmonary Disease and Sleep Apnea.

Antioxidants (Basel, Switzerland)·2025

Same author

AI4Food, a feasibility study for the implementation of automated devices in the nutritional advice and follow up within a weight loss intervention.

Clinical nutrition (Edinburgh, Scotland)·2025

Kernel Density Estimation-K-Nearest Neighbors (KDE-KNN) generates high-quality synthetic data for AI models, improving performance and protecting patient privacy. This method addresses data scarcity and privacy concerns in healthcare applications.

Area of Science:

Biomedical Informatics
Artificial Intelligence in Healthcare
Data Science

Background:

Machine learning (AI) models offer advances in diagnostics and personalized medicine.
Challenges include scarce, low-quality datasets and patient data privacy concerns.
Synthetic data generation aims to address these issues, but many methods fail to balance privacy and accuracy for tabular data.

Purpose of the Study:

To introduce Kernel Density Estimation-K-Nearest Neighbors (KDE-KNN), a novel privacy-aware method for generating tabular synthetic data.
To evaluate KDE-KNN's performance against state-of-the-art techniques using a sepsis detection case study.
To assess both the data utility and privacy protection capabilities of the proposed method.

Main Methods:

Proposed Kernel Density Estimation-K-Nearest Neighbors (KDE-KNN) algorithm for privacy-aware synthetic data generation.

Keywords:

machine learning sepsis detection synthetic data

Related Experiment Videos

Last Updated: May 28, 2026

A Data-Driven Approach to Quantifying Immune States in Sepsis

A Data-Driven Approach to Quantifying Immune States in Sepsis

Published on: February 7, 2025

Evaluated performance using sepsis detection as a real-world case study.

Assessed data utility through model performance and privacy protection via re-identification risk analysis.

Main Results:

Models trained on KDE-KNN synthetic data outperformed those trained on real data in internal and external validation.
A support vector machine showed superior performance with synthetic data, attributed to balanced class distribution.
Privacy evaluation showed a lower re-identification risk for KDE-KNN generated data.

Conclusions:

KDE-KNN effectively generates high-quality synthetic data, preserving statistical fidelity and protecting sensitive information.
The method balances utility and privacy, creating representative datasets without exposing individual records.
KDE-KNN is a valuable tool for data-scarce, privacy-sensitive healthcare applications and beyond.